GPT Oss Safeguard 20b
groq/openai/gpt-oss-safeguard-20bGPT Oss Safeguard 20b is a reasoning model by OpenAI with function calling, web search, structured output — designed for complex, multi-step problem solving where accuracy matters more than speed. It supports a 131K token context window with up to 66K tokens of output. Priced at $0.075 per million input tokens and $0.3 per million output tokens, it is one of the most cost-efficient options in its class. Access GPT Oss Safeguard 20b through Inworld LLM Inference with OpenAI SDK compatibility, built-in failover, and intelligent routing across providers.
- Input
- $0.075
- Output
- $0.30
- Cache read
- $0.0375
- Context
- 131.1K
- Max output
- 65.5K
curl --fail-with-body https://api.inworld.ai/v1/chat/completions \
-H "Authorization: Basic $INWORLD_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "groq/openai/gpt-oss-safeguard-20b",
"messages": [{"role": "user", "content": "Hello"}],
"stream": true
}'Pricing and providers
Access GPT Oss Safeguard 20b through Inworld LLM Inference or speech to speech via Groq. By using the providers below you agree to their terms, listed under each provider's name in the Legal section.
| Modalities | |||||||
|---|---|---|---|---|---|---|---|
GroqThis pagegroq/openai/gpt-oss-safeguard-20b | $0.075 | $0.30 | $0.0375 | — | 131.1K | 65.5K | Text→Text |
Start building with GPT Oss Safeguard 20b
Access GPT Oss Safeguard 20b and every other model through LLM Inference or speech to speech. Create a free account and start in minutes.